From f74c04b6863ff727ac8b000ed68bbb0df0c79f0c Mon Sep 17 00:00:00 2001
From: corey-derochie-amd
 <161367113+corey-derochie-amd@users.noreply.github.com>
Date: Thu, 2 May 2024 09:18:25 -0600
Subject: [PATCH] Fixed spelling

---
 src/common.cu | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/common.cu b/src/common.cu
index bae774abc9..def6ca029e 100644
--- a/src/common.cu
+++ b/src/common.cu
@@ -653,7 +653,7 @@ testResult_t TimeTest(struct threadArgs* args, ncclDataType_t type, const char*
   if (cudaGraphLaunches >= 1) {
     // Begin cuda graph capture
     for (int i=0; i<args->nGpus; i++) {
-      // Thread local mdoe is needed for:
+      // Thread local mode is needed for:
       // - Multi-thread mode: where graph capture and instantiation can happen concurrently across threads
       // - P2P pre-connect: when there is no warm-up, P2P pre-connect is done during graph capture.
       //   Since pre-connect calls cudaMalloc, we cannot use global capture mode
@@ -703,7 +703,7 @@ testResult_t TimeTest(struct threadArgs* args, ncclDataType_t type, const char*
   if (cudaGraphLaunches >= 1) {
     // Begin cuda graph capture
     for (int i=0; i<args->nGpus; i++) {
-      // Thread local mdoe is needed for:
+      // Thread local mode is needed for:
       // - Multi-thread mode: where graph capture and instantiation can happen concurrently across threads
       // - P2P pre-connect: when there is no warm-up, P2P pre-connect is done during graph capture.
       //   Since pre-connect calls cudaMalloc, we cannot use global capture mode